人工智能自然语言处理临床应用的伦理研究  

The Ethical Study of the Application of Artificial Intelligence and Natural Language Processing in the Clinical Practice

作　　者：王琼[1] WANG Qiong(College of Foreign Languages,Nanjing Xiaozhuang University,Nanjing 211171,China)

机构地区：[1]南京晓庄学院外国语学院,江苏南京211171

出　　处：《医学与哲学》2023年第21期12-16,共5页Medicine and Philosophy

摘　　要：在高风险的医疗场域中,自然语言处理技术中的语言区隔和技术内在设计缺陷可能对诊疗行为和医疗体系带来严重风险,其语言区隔阻碍了不同群体的医疗伦理公正,技术自身的“黑箱”性质与不可解释性可能导致错诊误诊等问题,同时技术的过度使用破坏了医疗场域中的伦理关系,危及人类在技术及其应用中的主体性地位。为防止自然语言处理技术在临床应用中可能出现不良的伦理后果,我们需要发扬人的主观能动性主导自然语言技术的发展,依据自然语言处理协会公布的道德规范框架和行为准则,评估当前的应用现状,建构和提供一个有温度有弹性的伦理模型和行动指南。Language disparity in the Natural Language Processing(NLP)world and its inherent design defects may bring serious pitfalls to diagnostic behaviors and the healthcare system in high-risk medical settings.Also,language disparity in NLP hinders the justice in medical ethics,and the"Black Box"problem with unexplainability of NLP may lead to misdiagnoses,etc.Moreover,the excessive use of technology destroys the ethical relationship in the medical field,challenging human subjectivity in the application of NLP.To prevent the potential ethical risks of NLP in clinical practice,we should take the initiative to lead the development of NLP in accordance with the published framework and unified codes of ethics from the NLP Association,assess the current implications of NLP in clinical practice,build and provide a warm and resilient ethical model and guidelines for action.

关 键 词：自然语言处理 临床应用 伦理风险 伦理困境 伦理模型 

分 类 号：R-05[医药卫生]